Search results

With the development of intelligent technology, deep learning has made significant progress and has been widely used in various fields. Deep learning is data-driven, and its training process requires a large amount of data to improve model performance. However, labeled data is expensive and not readily available.

To address the above problem, researchers have integrated semi-supervised and deep learning, using a limited number of labeled data and many unlabeled data to train models. In this paper, Generative Adversarial Networks (GANs) are analyzed as an entry point. Firstly, we discuss the current research on GANs in image super-resolution applications, including supervised, unsupervised, and semi-supervised learning approaches. Secondly, based on semi-supervised learning, different optimization methods are introduced as an example of image classification. Eventually, experimental comparisons and analyses of existing semi-supervised optimization methods based on GANs will be performed.

Following the analysis of the selected studies, we summarize the problems that existed during the research process and propose future research directions.

This paper reviews and analyzes research on generative adversarial networks for image super-resolution and classification from various learning approaches. The comparative analysis of experimental results on current semi-supervised GAN optimizations is performed to provide a reference for further research.

Today's marketing is dominated by decision-making based on artificial intelligence and machine learning. This study focuses on one semi- and unsupervised machine learning technique, generative adversarial networks (GANs). GANs are a type of deep learning architecture capable of generating new data similar to the training data that were used to train it, and thus, it is designed to learn a generative model that can produce new samples. GANs have been used in multiple marketing areas, especially in creating images and video and providing customized consumer contents. Through providing a holistic picture of GANs, including its advantage, disadvantage, ethical considerations, and its current application, the study attempts to provide business some strategical orientations, including formulating strong marketing positioning, creating consumer lifetime values, and delivering desired marketing tactics in product, promotion, pricing, and distribution channel. Through using GANs, marketers will create unique experiences for consumers, build strategic focus, and gain competitive advantages. This study is an original endeavor in discussing GANs in marketing, offering fresh insights in this research topic.

Forecasting population movement trends is crucial for implementing effective policies to regulate labor force growth and understand demographic changes. Combining migration theory expertise and neural network technology can bring a fresh perspective to international migration forecasting research.

This study proposes a conditional generative adversarial neural network model incorporating the migration knowledge – conditional generative adversarial network (MK-CGAN). By using the migration knowledge to design the parameters, MK-CGAN can effectively address the limited data problem, thereby enhancing the accuracy of migration forecasts.

The model was tested by forecasting migration flows between different countries and had good generalizability and validity. The results are robust as the proposed solutions can achieve lesser mean absolute error, mean squared error, root mean square error, mean absolute percentage error and R² values, reaching 0.9855 compared to long short-term memory (LSTM), gated recurrent unit, generative adversarial network (GAN) and the traditional gravity model.

This study is significant because it demonstrates a highly effective technique for predicting international migration using conditional GANs. By incorporating migration knowledge into our models, we can achieve prediction accuracy, gaining valuable insights into the differences between various model characteristics. We used SHapley Additive exPlanations to enhance our understanding of these differences and provide clear and concise explanations for our model predictions. The results demonstrated the theoretical significance and practical value of the MK-CGAN model in predicting international migration.

Online news websites provide huge amounts of timely news, bringing the challenge of recommending personalized news articles. Generative adversarial networks (GAN) based on collaborative filtering (CFGAN) can achieve effective recommendation quality. However, CFGAN ignores item contents, which contain more latent preference features than just user ratings. It is important to consider both ratings and item contents in making preference predictions. This study aims to improve news recommendation by proposing a GAN-based news recommendation model considering both ratings (implicit feedback) and the latent features of news content.

The collaborative topic modeling (CTM) can improve user preference prediction by combining matrix factorization (MF) with latent topics of item content derived from latent topic modeling. This study proposes a novel hybrid news recommendation model, Hybrid-CFGAN, which modifies the architecture of the CFGAN model with enhanced preference learning from the CTM. The proposed Hybrid-CFGAN model contains parallel neural networks – original rating-based preference learning and CTM-based preference learning, which consider both ratings and news content with user preferences derived from the CTM model. A tunable parameter is used to adjust the weights of the two preference learnings, while concatenating the preference outputs of the two parallel neural networks.

This study uses the dataset collected from an online news website, NiusNews, to conduct an experimental evaluation. The results show that the proposed Hybrid-CFGAN model can achieve better performance than the state-of-the-art GAN-based recommendation methods. The proposed novel Hybrid-CFGAN model can enhance existing GAN-based recommendation and increase the performance of preference predictions on textual content such as news articles.

As the existing CFGAN model does not consider content information and solely relies on history logs, it may not be effective in recommending news articles. Our proposed Hybrid-CFGAN model modified the architecture of the CFGAN generator by adding a parallel neural network to gain the relevant information from news content and user preferences derived from the CTM model. The novel idea of adjusting the preference learning from two parallel neural networks – original rating-based preference learning and CTM-based preference learning – contributes to improve the recommendation quality of the proposed model by considering both ratings and latent preferences derived from item contents. The proposed novel recommendation model can improve news recommendation, thereby increasing the commercial value of news media platforms.

Nowadays, artificial intelligence (AI) technology has demonstrated extensive applications in the field of art design. Attribute editing is an important means to realize clothing style and color design via computer language, which aims to edit and control the garment image based on the specified target attributes while preserving other details from the original image. The current image attribute editing model often generates images containing missing or redundant attributes. To address the problem, this paper aims for a novel design method utilizing the Fashion-attribute generative adversarial network (AttGAN) model was proposed for image attribute editing specifically tailored to women’s blouses.

The proposed design method primarily focuses on optimizing the feature extraction network and loss function. To enhance the feature extraction capability of the model, an increase in the number of layers in the feature extraction network was implemented, and the structure similarity index measure (SSIM) loss function was employed to ensure the independent attributes of the original image were consistent. The characteristic-preserving virtual try-on network (CP_VTON) dataset was used for train-ing to enable the editing of sleeve length and color specifically for women’s blouse.

The experimental results demonstrate that the optimization model’s generated outputs have significantly reduced problems related to missing attributes or visual redundancy. Through a comparative analysis of the numerical changes in the SSIM and peak signal-to-noise ratio (PSNR) before and after the model refinement, it was observed that the improved SSIM increased substantially by 27.4%, and the PSNR increased by 2.8%, serving as empirical evidence of the effectiveness of incorporating the SSIM loss function.

The proposed algorithm provides a promising tool for precise image editing of women’s blouses based on the GAN. This introduces a new approach to eliminate semantic expression errors in image editing, thereby contributing to the development of AI in clothing design.

This study presents an ontological approach to assess the architectural outputs of generative adversarial networks. This paper aims to assess the performance of the generative adversarial network in representing building knowledge.

The proposed ontological assessment consists of five steps. These are, respectively, creating an architectural data set, developing ontology for the architectural data set, training the You Only Look Once object detection with labels within the proposed ontology, training the StyleGAN algorithm with the images in the data set and finally, detecting the ontological labels and calculating the ontological relations of StyleGAN-generated pixel-based architectural images. The authors propose and calculate ontological identity and ontological inclusion metrics to assess the StyleGAN-generated ontological labels. This study uses 300 bay window images as an architectural data set for the ontological assessment experiments.

The ontological assessment provides semantic-based queries on StyleGAN-generated architectural images by checking the validity of the building knowledge representation. Moreover, this ontological validity reveals the building element label-specific failure and success rates simultaneously.

This study contributes to the assessment process of the generative adversarial networks through ontological validity checks rather than only conducting pixel-based similarity checks; semantic-based queries can introduce the GAN-generated, pixel-based building elements into the architecture, engineering and construction industry.

Purveyors of fake news perpetuate information that can harm society, including businesses. Social media's reach quickly amplifies distortions of fake news. Research has not yet fully explored the mechanisms of such adversarial behavior or the adversarial techniques of machine learning that might be deployed to detect fake news. Debiasing techniques are also explored to combat against the generation of fake news using adversarial data. The purpose of this paper is to present the challenges and opportunities in fake news detection.

First, this paper provides an overview of adversarial behaviors and current machine learning techniques. Next, it describes the use of long short-term memory (LSTM) to identify fake news in a corpus of articles. Finally, it presents the novel adversarial behavior approach to protect targeted business datasets from attacks.

This research highlights the need for a corpus of fake news that can be used to evaluate classification methods. Adversarial debiasing using IBM's Artificial Intelligence Fairness 360 (AIF360) toolkit can improve the disparate impact of unfavorable characteristics of a dataset. Debiasing also demonstrates significant potential to reduce fake news generation based on the inherent bias in the data. These findings provide avenues for further research on adversarial collaboration and robust information systems.

Adversarial debiasing of datasets demonstrates that by reducing bias related to protected attributes, such as sex, race and age, businesses can reduce the potential of exploitation to generate fake news through adversarial data.

Data quality and data resolution are essential for computer vision tasks like medical image processing, object detection, pattern recognition and so on. Super-resolution is a way to increase the image resolution, and super-resolved images contain more information compared to their low-resolution counterparts. The purpose of this study is analyzing the effects of the super resolution models trained before on object detection for aerial images.

Two different models were trained using the Super-Resolution Generative Adversarial Network (SRGAN) architecture on two aerial image data sets, the xView and the Dataset for Object deTection in Aerial images (DOTA). This study uses these models to increase the resolution of aerial images for improving object detection performance. This study analyzes the effects of the model with the best perceptual index (PI) and the model with the best RMSE on object detection in detail.

Super-resolution increases the object detection quality as expected. But, the super-resolution model with better perceptual quality achieves lower mean average precision results compared to the model with better RMSE. It means that the model with a better PI is more meaningful to human perception but less meaningful to computer vision.

The contributions of the authors to the literature are threefold. First, they do a wide analysis of SRGAN results for aerial image super-resolution on the task of object detection. Second, they compare super-resolution models with best PI and best RMSE to showcase the differences on object detection performance as a downstream task first time in the literature. Finally, they use a transfer learning approach for super-resolution to improve the performance of object detection.

To improve the speed and accuracy of turbine blade film cooling design process, the most advanced deep learning models were introduced into this study to investigate the most suitable define for prediction work. This paper aims to create a generative surrogate model that can be applied on multi-objective optimization problems.

The latest backbone in the field of computer vision (Swin-Transformer, 2021) was introduced and improved as the surrogate function for prediction of the multi-physics field distribution (film cooling effectiveness, pressure, density and velocity). The basic samples were generated by Latin hypercube sampling method and the numerical method adopt for the calculation was validated experimentally at first. The training and testing samples were calculated at experimental conditions. At last, the surrogate model predicted results were verified by experiment in a linear cascade.

The results indicated that comparing with the Multi-Scale Pix2Pix Model, the Swin-Transformer U-Net model presented higher accuracy and computing speed on the prediction of contour results. The computation time for each step of the Swin-Transformer U-Net model is one-third of the original model, especially in the case of multi-physics field prediction. The correlation index reached more than 99.2% and the first-order error was lower than 0.3% for multi-physics field. The predictions of the data-driven surrogate model are consistent with the predictions of the computational fluid dynamics results, and both are very close to the experimental results. The application of the Swin-Transformer model on enlarging the different structure samples will reduce the cost of numerical calculations as well as experiments.

The number of U-Net layers and sample scales has a proper relationship according to equation (8). Too many layers of U-Net will lead to unnecessary nonlinear variation, whereas too few layers will lead to insufficient feature extraction. In the case of Swin-Transformer U-Net model, incorrect number of U-Net layer will reduce the prediction accuracy. The multi-scale Pix2Pix model owns higher accuracy in predicting a single physical field, but the calculation speed is too slow. The Swin-Transformer model is fast in prediction and training (nearly three times faster than multi Pix2Pix model), but the predicted contours have more noise. The neural network predicted results and numerical calculations are consistent with the experimental distribution.

This paper creates a generative surrogate model that can be applied on multi-objective optimization problems. The generative adversarial networks using new backbone is chosen to adjust the output from single contour to multi-physics fields, which will generate more results simultaneously than traditional surrogate models and reduce the time-cost. And it is more applicable to multi-objective spatial optimization algorithms. The Swin-Transformer surrogate model is three times faster to computation speed than the Multi Pix2Pix model. In the prediction results of multi-physics fields, the prediction results of the Swin-Transformer model are more accurate.

This paper aims to improve the manufacturability of additive manufacturing (AM) for topology-optimized (TO) structures. Enhancement of manufacturability focuses on modifying geometric constraints and classifying the building orientation (BO) of AM parts to reduce stresses and support structures (SSs). To this end, artificial intelligence (AI) networks are being developed to automate design for additive manufacturing (DfAM).

This study considers three geometric constraints for their correction by convolutional autoencoders (CAEs) and transfer learning (TL). Furthermore, BOs of AM parts are classified using generative adversarial (GAN) and classification networks to reduce the SS. To verify the results, finite element analysis (FEA) is performed to compare the stresses of modified components with the original ones. Moreover, one sample is produced by the laser-based powder bed fusion (LB-PBF) in the BO predicted by the AI to observe its SSs.

CAE and TL resulted in promoting the manufacturability of TO components. FEA demonstrated that enhancing manufacturability leads to a 50% reduction in stresses. Additionally, training GAN and pre-training the ResNet-18 resulted in 80%, 95% and 96% accuracy for training, validation and testing. The production of a sample with LB-PBF demonstrated that the predicted BO by ResNet-18 does not require SSs.

This paper provides an automatic platform for DfAM of TO parts. Consequently, complex TO parts can be designed most feasibly and manufactured by AM technologies with minimal material usage, residual stresses and distortions.